Provides OCR (Optical Character Recognition) capabilities through MCP, including text extraction and document layout parsing to Markdown. Supports multiple PaddleOCR models like PP-OCRv5, PP-OCRv6, and PP-StructureV3.
Enables OCR-based text, table, handwriting, and formula recognition from images via MCP, supporting local files and URLs for integration with AI assistants.
Enables MCP clients to perform local OCR on image files or base64-encoded images, returning recognized text with optional bounding boxes and confidence scores.
